© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4780
    Prev
    Next
    INDEX
    Explanations

    Appearance or seeming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     look
    -0.68
     looking
    -0.57
     looks
    -0.51
    <bos>
    -0.51
     looked
    -0.50
    look
    -0.49
     Look
    -0.48
    Look
    -0.47
    ca
    -0.46
     appearance
    -0.44
    POSITIVE LOGITS
    providedIn
    0.95
    GEBURTSDATUM
    0.82
     pinulongan
    0.81
    parsedMessage
    0.81
    ANTLR
    0.80
     iprot
    0.80
    migrationBuilder
    0.76
    writeFieldEnd
    0.75
     BorderRadius
    0.73
    amaño
    0.71
    Activations Density 0.033%

    No Known Activations